Nonlinear Stochastic Density Steering via Gaussian Mixture Schrodinger Bridges and Multiple Linearizations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910161579278336 |
|---|---|
| author | Mosso, Mattia Rapakoulias, George Guan, Yue Tsiotras, Panagiotis |
| author_facet | Mosso, Mattia Rapakoulias, George Guan, Yue Tsiotras, Panagiotis |
| contents | The paper studies the optimal density steering problem for nonlinear continuous-time stochastic systems. To accurately capture nonlinear dynamics in high-uncertainty regions that deviate significantly from a nominal linearization point, we introduce the concept of Multiple Distribution-to-Distribution Linearization. The proposed approach first approximates the boundary distributions using Gaussian Mixture Models (GMMs), and decomposes the original nonlinear problem into a collection of Gaussian-to-Gaussian Optimal Covariance Steering (OCS) subproblems between pairs of mixture components. Each elementary OCS problem is solved via local linearization around the mean trajectory connecting the corresponding initial and terminal Gaussian components. The resulting elementary policies are then combined according to their associated conditional densities. We prove that the proposed multi-linearization approach yields tighter approximation error bounds than single-linearization for a broad class of problems. The effectiveness of the approach is demonstrated through numerical experiments on an Earth-to-Mars orbit transfer scenario. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15576 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Nonlinear Stochastic Density Steering via Gaussian Mixture Schrodinger Bridges and Multiple Linearizations Mosso, Mattia Rapakoulias, George Guan, Yue Tsiotras, Panagiotis Systems and Control The paper studies the optimal density steering problem for nonlinear continuous-time stochastic systems. To accurately capture nonlinear dynamics in high-uncertainty regions that deviate significantly from a nominal linearization point, we introduce the concept of Multiple Distribution-to-Distribution Linearization. The proposed approach first approximates the boundary distributions using Gaussian Mixture Models (GMMs), and decomposes the original nonlinear problem into a collection of Gaussian-to-Gaussian Optimal Covariance Steering (OCS) subproblems between pairs of mixture components. Each elementary OCS problem is solved via local linearization around the mean trajectory connecting the corresponding initial and terminal Gaussian components. The resulting elementary policies are then combined according to their associated conditional densities. We prove that the proposed multi-linearization approach yields tighter approximation error bounds than single-linearization for a broad class of problems. The effectiveness of the approach is demonstrated through numerical experiments on an Earth-to-Mars orbit transfer scenario. |
| title | Nonlinear Stochastic Density Steering via Gaussian Mixture Schrodinger Bridges and Multiple Linearizations |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2604.15576 |